Server providing Argo CD integration for MCP clients.
Nothing to run from here
ComputeNexa is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
44
downloads in 30d
local
runs on your machine
15
tools declared
What it does
Find, launch and stop private GPUs on ComputeNexa, with a quote before anything is charged.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'CNX_API_KEY=${CNX_API_KEY}' --transport stdio computenexa-mcp '--' uvx computenexa-mcp
# 2 — ask your agent for something these tools do
# whoami, list_gpus, list_apps and 12 more
It needs CNX_API_KEY: this reads it from your environment, so export it first.
ComputeNexa costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CGAll 1 server
computenexa-gpuInfrastructure1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts ComputeNexa as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads CNX_API_KEY (A ComputeNexa API key (dashboard, API keys): Look only, or Launch and stop) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx CNX_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'CNX_API_KEY=${CNX_API_KEY}' --transport stdio computenexa-mcp '--' uvx computenexa-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: CNX_API_KEY — A ComputeNexa API key (dashboard, API keys): Look only, or Launch and stop. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Who this server's API key acts as: email, team and role, the team's balance and GPU limit, and whether the key may launch and stop machines.
Takes no parameters.
GPUs with live prices (US dollars per GPU per hour) and stock, cheapest first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| app | string | no | Only GPUs that run this app (see list_apps), e.g. chat |
| region | string | no | any = anywhere; us; ca = Canada |
| min_memory_gb | integer | no | At least this much GPU memory |
| include_sold_out | boolean | no | Also list GPUs not for sale right now |
The apps a GPU can start with (basic, datascience, chat, imagegen, modelapi, voice): what each is for, the models it offers and which model we recommend per GPU memory. Give app for the software installed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| app | string | no | One app, to also see what's installed in it |
| package | string | no | With app: find this package's version, e.g. torch |
Your machines, newest first: state, GPU, app, price, time left and cost so far.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| active_only | boolean | no | Only starting or running machines |
| whole_team | boolean | no | The whole team's machines (owners and admins) |
| limit | integer | no | — |
One machine: its state, how to connect (SSH command, browser apps, API or endpoint address), time left, keep-running status and costs. Never its keys.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| machine_id | string | yes | e.g. cnx-7f3a9c |
Spending and GPU-hours over the last N days, by GPU, app, day and project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | The last N days |
Finished sessions and what each cost in the end (charged minus refunded).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | Sessions that ended in the last N days |
| limit | integer | no | — |
Saved projects (files restored into ~/work on machines launched with them) and their size.
Takes no parameters.
Endpoints: stable HTTPS addresses for your own server on a machine's port 8000, and the machine each points at now. Never their keys.
Takes no parameters.
Launch a GPU machine. Costs money: call first with confirm=false to get a quote (nothing happens), show it to the person, and only after they agree call again with the same arguments, confirm=true and expected_total_usd. The booked time is charged up front from the team's balance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| gpu | string | yes | GPU slug from list_gpus, e.g. rtx-a6000 |
| app | string | yes | App from list_apps, e.g. datascience |
| hours | number | yes | How long to book; unused time is refunded |
| gpu_count | integer | no | — |
| region | string | no | Where it must run |
| model | string | no | For apps with models; left out = our recommendation for this GPU |
| project | string | no | Project name or id to restore into ~/work and save back |
| endpoint | string | no | Endpoint name or id this machine serves |
| label | string | no | A name for the machine |
| keep_running_hours | integer | no | Renew this many hours at a time until stopped |
| confirm | boolean | no | false = only quote (default); true = launch, after the person agreed to the quote |
| expected_total_usd | number | no | With confirm=true: the quote's total_usd the person agreed to |
Add time to a machine at the price it launched with. Costs money: quote first (confirm=false), then confirm=true with expected_total_usd once the person agrees.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| machine_id | string | yes | — |
| hours | number | yes | Time to add |
| confirm | boolean | no | false = only quote; true = extend, after the person agreed |
| expected_total_usd | number | no | With confirm=true: the quoted total_usd |
Keep running: the machine renews itself hours at a time from the team's balance, at its launch price, until it's stopped. Turning it on spends money at every renewal: quote first, then confirm=true with expected_renewal_usd. Turning it off (hours=null) needs no confirmation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| machine_id | string | yes | — |
| hours | integer | no | Renew this many hours at a time; null = turn off (it stops when its paid time ends) |
| confirm | boolean | no | Turning on: false = only quote; true = turn on, after the person agreed |
| expected_renewal_usd | number | no | With confirm=true: the quoted renewal_usd |
End a machine now: stopped if running, cancelled with a full refund if still starting. Files outside a project are deleted; a project is saved first. Unused time is refunded. Can't be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| machine_id | string | yes | — |
A new Endpoint (owners and admins): a stable HTTPS address and key for your own server on port 8000, e.g.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | e.g. the customer it serves |
An Endpoint's key (owners and admins). Only when the person asks for it: it gives access to their server.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| endpoint | string | yes | Endpoint name or id |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ComputeNexa or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 0.1.0 · scanned 1 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digestb41844f0564a1d09f021a50022a5cddcd834d75874a630e24c535d6dad72539f
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
6 of the 15 recovered tools are registered only when scope == "read" is false (src/computenexa_mcp/server.py:409) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 9.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
9 tools are registered unconditionally · 6 more only when scope == "read" is false (src/computenexa_mcp/server.py:409) — typically when a key or option is configured. All 15 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| whoami | no tags | |
| list_gpus | no tags | |
| list_apps | no tags | |
| list_machines | no tags | |
| get_machine | no tags | |
| get_usage | no tags | |
| list_receipts | no tags | |
| list_projects | no tags | |
| list_endpoints | no tags | |
| launch_machine conditional | no tags | |
| extend_machine conditional | no tags | |
| set_keep_running conditional | no tags | |
| stop_machine conditional | no tags | |
| create_endpoint conditional | no tags | |
| get_endpoint_key conditional | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestb41844f0564a1d09
Scanned2026-11-01
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish ComputeNexa can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.